Virtualizing Communication for Hybrid and Diversity-Aware Collective Adaptive Systems

Page 1

Virtualizing Communication for Hybrid and Diversity-Aware Collective Adaptive Systems Philipp Zeppezauer, Ognjen Scekic, Hong-Linh Truong, and Schahram Dustdar Distributed Systems Group, Vienna University of Technology, Austria Email: {zeppezauer,oscekic,truong,dustdar}@dsg.tuwien.ac.at

Abstract. Hybrid and Diversity-Aware Collective Adaptive Systems (HDA-CAS) form a broad class of highly distributed systems comprising a number of heterogeneous human-based and machine-based computing (service) units. These units collaborate in ad-hoc formed, dynamicallyadaptive collectives. The flexibility of these collectives makes them suitable for processing elaborate tasks, but at the same time, building a system to support diverse communication types in such collectives is challenging. In this paper, we address the fundamental communication challenges for HDA-CAS. We present the design of a middleware for virtualizing communication within and among collectives of diverse types of service units. The middleware is able to handle numerous, intermittently available, human and software-based service units, and manages the notion of collectivity transparently to the programmer. A prototype implementation for validation purpose is also provided.

1

Introduction

Collective Adaptive System (CAS ) [2] is an umbrella-term denoting distributed systems comprised of multiple autonomous computing/service units with different individual properties, but with the fundamental property of collectiveness. Collectiveness implies that the individual units need to communicate and collaborate in order to reach common decisions, or perform tasks jointly. Adaptiveness is another basic property of CASs, implying open systems where units may join and leave, and dynamically alter collective compositions or task execution goals. CASs come in a variety of forms. Hybrid and Diversity-Aware CASs (HDACAS s) [1] additionally add the heterogeneity to the founding principles. This means that they inherently support communication and collaboration among different types of units, such as software, people and sensors. Motivation. Let us consider a smart-city maintenance provider (MP ) – a company running a monitoring center covering thousands of sensors and equipment systems geographically dispersed in numerous smart buildings (e.g., Galaxy1 ). The MP provides the centralized service of both predictive and corrective maintenance to its customers (building/equipment owners/tenants). This means that MP control centers actively monitor events originating from various 1

Pacific Controls Galaxy. http://www.pacific-galaxy.com/


Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.